crown 0.1.0 → 0.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/ChangeLog +4 -0
- data/README.rdoc +14 -11
- data/VERSION +1 -1
- data/crown.gemspec +15 -5
- data/example/entrylist.rb +69 -0
- data/example/fbcount.rb +1 -1
- data/example/hbentry.rb +1 -1
- data/example/rtcount.rb +1 -0
- data/example/twcount.rb +1 -1
- data/example/{annual.rb → urilist.rb} +21 -26
- data/lib/crown.rb +1 -1
- data/{example/hbtrace.rb → lib/crown/amazon.rb} +8 -23
- data/lib/crown/amazon/crawler.rb +159 -0
- data/lib/crown/amazon/ecs.rb +385 -0
- data/lib/crown/amazon/entrylist.rb +171 -0
- data/lib/crown/backtype.rb +2 -2
- data/lib/crown/buzzurl.rb +2 -2
- data/lib/crown/cgm.rb +8 -0
- data/lib/crown/cgm/countable.rb +1 -1
- data/lib/crown/cgm/summarizable.rb +1 -1
- data/lib/crown/delicious.rb +2 -2
- data/lib/crown/facebook.rb +4 -4
- data/lib/crown/facebook/entry.rb +5 -3
- data/lib/crown/google.rb +38 -0
- data/lib/crown/google/plusone.rb +65 -0
- data/lib/crown/google/plusone/counter.rb +102 -0
- data/lib/crown/hatena/bookmark.rb +7 -7
- data/lib/crown/hatena/bookmark/entry.rb +70 -68
- data/lib/crown/hatena/bookmark/entrylist.rb +98 -0
- data/lib/crown/hatena/bookmark/urilist.rb +349 -0
- data/lib/crown/http-wrapper.rb +0 -1
- data/lib/crown/linkedin.rb +60 -0
- data/lib/crown/linkedin/counter.rb +81 -0
- data/lib/crown/livedoor/clip.rb +2 -2
- data/lib/crown/livedoor/clip/counter.rb +1 -1
- data/lib/crown/livedoor/reader.rb +2 -2
- data/lib/crown/topsy.rb +2 -3
- data/lib/crown/tweetmeme.rb +2 -2
- data/lib/crown/twitter.rb +1 -1
- data/lib/crown/twitter/uri.rb +2 -2
- data/lib/crown/twitter/user.rb +4 -4
- data/lib/crown/twitter/user/entry.rb +26 -6
- data/lib/crown/yahoo/bookmark.rb +3 -7
- data/test/crown-test.rb +34 -12
- metadata +17 -7
- data/lib/crown/hatena/bookmark/linktrace.rb +0 -135
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: crown
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 25
|
5
5
|
prerelease:
|
6
6
|
segments:
|
7
7
|
- 0
|
8
8
|
- 1
|
9
|
-
-
|
10
|
-
version: 0.1.
|
9
|
+
- 1
|
10
|
+
version: 0.1.1
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- clown
|
@@ -15,7 +15,7 @@ autorequire:
|
|
15
15
|
bindir: bin
|
16
16
|
cert_chain: []
|
17
17
|
|
18
|
-
date: 2012-01
|
18
|
+
date: 2012-03-01 00:00:00 Z
|
19
19
|
dependencies:
|
20
20
|
- !ruby/object:Gem::Dependency
|
21
21
|
name: json
|
@@ -77,17 +77,21 @@ files:
|
|
77
77
|
- Rakefile
|
78
78
|
- VERSION
|
79
79
|
- crown.gemspec
|
80
|
-
- example/annual.rb
|
81
80
|
- example/cgmcount.rb
|
81
|
+
- example/entrylist.rb
|
82
82
|
- example/fbcount.rb
|
83
83
|
- example/feedcount.rb
|
84
84
|
- example/hbcount.rb
|
85
85
|
- example/hbentry.rb
|
86
|
-
- example/hbtrace.rb
|
87
86
|
- example/rtcount.rb
|
88
87
|
- example/sbmcount.rb
|
89
88
|
- example/twcount.rb
|
89
|
+
- example/urilist.rb
|
90
90
|
- lib/crown.rb
|
91
|
+
- lib/crown/amazon.rb
|
92
|
+
- lib/crown/amazon/crawler.rb
|
93
|
+
- lib/crown/amazon/ecs.rb
|
94
|
+
- lib/crown/amazon/entrylist.rb
|
91
95
|
- lib/crown/backtype.rb
|
92
96
|
- lib/crown/backtype/counter.rb
|
93
97
|
- lib/crown/buzzurl.rb
|
@@ -100,12 +104,18 @@ files:
|
|
100
104
|
- lib/crown/facebook.rb
|
101
105
|
- lib/crown/facebook/counter.rb
|
102
106
|
- lib/crown/facebook/entry.rb
|
107
|
+
- lib/crown/google.rb
|
108
|
+
- lib/crown/google/plusone.rb
|
109
|
+
- lib/crown/google/plusone/counter.rb
|
103
110
|
- lib/crown/hatena.rb
|
104
111
|
- lib/crown/hatena/bookmark.rb
|
105
112
|
- lib/crown/hatena/bookmark/counter.rb
|
106
113
|
- lib/crown/hatena/bookmark/entry.rb
|
107
|
-
- lib/crown/hatena/bookmark/
|
114
|
+
- lib/crown/hatena/bookmark/entrylist.rb
|
115
|
+
- lib/crown/hatena/bookmark/urilist.rb
|
108
116
|
- lib/crown/http-wrapper.rb
|
117
|
+
- lib/crown/linkedin.rb
|
118
|
+
- lib/crown/linkedin/counter.rb
|
109
119
|
- lib/crown/livedoor.rb
|
110
120
|
- lib/crown/livedoor/clip.rb
|
111
121
|
- lib/crown/livedoor/clip/counter.rb
|
@@ -1,135 +0,0 @@
|
|
1
|
-
# -*- coding: utf-8 -*-
|
2
|
-
# --------------------------------------------------------------------------- #
|
3
|
-
#
|
4
|
-
# hatena/bookmark/linktrace.rb
|
5
|
-
#
|
6
|
-
# Copyright (c) 2008 - 2011, clown.
|
7
|
-
#
|
8
|
-
# Redistribution and use in source and binary forms, with or without
|
9
|
-
# modification, are permitted provided that the following conditions
|
10
|
-
# are met:
|
11
|
-
#
|
12
|
-
# - Redistributions of source code must retain the above copyright
|
13
|
-
# notice, this list of conditions and the following disclaimer.
|
14
|
-
# - Redistributions in binary form must reproduce the above copyright
|
15
|
-
# notice, this list of conditions and the following disclaimer in the
|
16
|
-
# documentation and/or other materials provided with the distribution.
|
17
|
-
# - No names of its contributors may be used to endorse or promote
|
18
|
-
# products derived from this software without specific prior written
|
19
|
-
# permission.
|
20
|
-
#
|
21
|
-
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
22
|
-
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
23
|
-
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
24
|
-
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
25
|
-
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
26
|
-
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
|
27
|
-
# TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
28
|
-
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
29
|
-
# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
30
|
-
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
31
|
-
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
32
|
-
#
|
33
|
-
# --------------------------------------------------------------------------- #
|
34
|
-
module Crown
|
35
|
-
module Hatena
|
36
|
-
module Bookmark
|
37
|
-
# --------------------------------------------------------------- #
|
38
|
-
#
|
39
|
-
# LinkTrace
|
40
|
-
#
|
41
|
-
# �w�肵�� Web �T�C�g�̂͂Ăȃu�b�N�}�[�N�ꗗ���珇�� URL ��
|
42
|
-
# �擾����N���X�D2 �y�[�W�ڈȍ~�̌��ʂ́Chtml �̃w�b�_����
|
43
|
-
# next ��������y�[�W�� URL �𐄑����Ď擾����D
|
44
|
-
#
|
45
|
-
# --------------------------------------------------------------- #
|
46
|
-
class LinkTrace
|
47
|
-
@@reserved = [ "/hotentry", "/entrylist", "/news", "/video", "/asin" ]
|
48
|
-
|
49
|
-
# ----------------------------------------------------------- #
|
50
|
-
# initialize
|
51
|
-
# ----------------------------------------------------------- #
|
52
|
-
def initialize(path, proxy_host = nil, proxy_port = nil)
|
53
|
-
@session = Crown::HTTPWrapper.new("b.hatena.ne.jp", 80, proxy_host, proxy_port)
|
54
|
-
@basename = String.new
|
55
|
-
@basename.concat("/") if (path[0] != 47)
|
56
|
-
@basename.concat(path)
|
57
|
-
@basename.concat("/") if (@basename.match(/^\/[\w\-]+$/) != nil && !@@reserved.include?(@basename))
|
58
|
-
@path = String.new(@basename)
|
59
|
-
end
|
60
|
-
|
61
|
-
# ----------------------------------------------------------- #
|
62
|
-
# reset
|
63
|
-
# ----------------------------------------------------------- #
|
64
|
-
def reset()
|
65
|
-
@path = String.new(@basename)
|
66
|
-
@session.finish if (@session.active?)
|
67
|
-
return self
|
68
|
-
end
|
69
|
-
|
70
|
-
# ----------------------------------------------------------- #
|
71
|
-
#
|
72
|
-
# more?
|
73
|
-
#
|
74
|
-
# �܂��擾�ł��� URL �����݂��邩�ǂ����肷��Dmore?()
|
75
|
-
# �� html �� next �������玟�̃y�[�W�������ł��Ă��邩
|
76
|
-
# �ǂ����Ŕ��肵�Ă���D
|
77
|
-
#
|
78
|
-
# ----------------------------------------------------------- #
|
79
|
-
def more?()
|
80
|
-
return @path != nil
|
81
|
-
end
|
82
|
-
|
83
|
-
# ----------------------------------------------------------- #
|
84
|
-
#
|
85
|
-
# get
|
86
|
-
#
|
87
|
-
# �ΏۂƂȂ�͂Ăȃu�b�N�}�[�N URL ��Ԃ��Dget() �� html ��
|
88
|
-
# next �������琄�����ꂽ�u���݂̃y�[�W�v�ɗ���Ă���
|
89
|
-
# �S�Ă̂͂Ăȃu�b�N�}�[�N URL ��z��Ɋi�[���ĕԂ��D
|
90
|
-
#
|
91
|
-
# ----------------------------------------------------------- #
|
92
|
-
def get()
|
93
|
-
result = Array.new
|
94
|
-
|
95
|
-
return result if (@path == nil)
|
96
|
-
response = @session.get(@path)
|
97
|
-
return result if (response == nil || response.code.to_i != 200)
|
98
|
-
guess(response.body)
|
99
|
-
|
100
|
-
html = Nokogiri::HTML.parse(response.body)
|
101
|
-
block = html.search('//ul[starts-with(@class, "hotentry")]')
|
102
|
-
block = html.search('//ul[starts-with(@class, "videolist")]') if block.empty?
|
103
|
-
return result if block.empty?
|
104
|
-
block[0].search("h3/a").each { |node|
|
105
|
-
result.push(node['href'])
|
106
|
-
}
|
107
|
-
|
108
|
-
# �������[�v����ꍇ������̂ŁC���݂̃y�[�W���� 1�������ʂ�
|
109
|
-
# �擾�ł��Ȃ��Ƃ��͂���ȏ�̌������~�߂�D
|
110
|
-
@path = nil if (result.empty?)
|
111
|
-
|
112
|
-
return result
|
113
|
-
end
|
114
|
-
|
115
|
-
private
|
116
|
-
# ----------------------------------------------------------- #
|
117
|
-
# guess
|
118
|
-
# ----------------------------------------------------------- #
|
119
|
-
def guess(str)
|
120
|
-
link = str.scan(/<link rel="next" href="(.+?)".*?>/m).to_s
|
121
|
-
if (link.empty?)
|
122
|
-
@path = nil
|
123
|
-
elsif (link[0] == 47)
|
124
|
-
@path = link
|
125
|
-
elsif (link[0] == 63)
|
126
|
-
@path.gsub!(/\?.*$/, "")
|
127
|
-
@path.concat(link)
|
128
|
-
else
|
129
|
-
@path = @basename + link
|
130
|
-
end
|
131
|
-
end
|
132
|
-
end # LinkTrace
|
133
|
-
end # Bookmark
|
134
|
-
end # Hatena
|
135
|
-
end # Crown
|